Training Description
Key Takeaways
- Explores the intersection of artificial intelligence, machine learning, and security/privacy
- Focuses on adversarial machine learning, AI safety, and ethical implications
- Targets academic researchers, industry practitioners, and professionals in AI, ML, and cybersecurity
- Addresses challenges in securing AI/ML systems and mitigating AI misuse
- Emphasizes thought leadership, education, and community building in AI security
The 19th ACM Workshop on Artificial Intelligence and Security (AISec 2026) will take place from November 15 to 19, 2026, in The Hague, Netherlands. This event is co-located with the 33rd ACM Conference on Computer and Communications Security, providing a unique platform for the exchange of ideas at the forefront of AI, machine learning, and cybersecurity.
Event Overview
AISec 2026 serves as a leading venue for presenting and discussing the latest research at the intersection of artificial intelligence, machine learning, and security/privacy. The workshop brings together experts to address the growing use of AI and ML in security-sensitive domains, as well as the challenges posed by adversarial threats and privacy concerns.
The event encourages original research, position papers, and systematization-of-knowledge contributions. There is a strong emphasis on ethical considerations and transparency, particularly regarding the use of generative AI in research. Attendees can expect a mix of paper presentations, poster sessions, and interactive discussions.
Main Topics and Themes
Key topics include adversarial machine learning, security of AI/ML systems, robust statistics, privacy-preserving data mining, and computer forensics. The workshop also covers spam and phishing detection, intrusion detection, malware analysis, data anonymization, cyber-threat intelligence, and secure multiparty computation.
Additional areas of focus are model confidentiality, AI misuse such as the use of large language models for hacking or misinformation, AI safety, alignment, oversight, red-teaming, societal-scale risks, and AI ethics. These themes reflect the workshop’s commitment to advancing both the technical and ethical dimensions of AI security.
Audience and Impact
The workshop is designed for academic researchers, industry practitioners, and professionals working in AI, machine learning, cybersecurity, and privacy. Typical attendees include security researchers, data scientists, AI/ML engineers, privacy officers, academic faculty, PhD students, and technical leads from universities, research institutes, and technology companies.
AISec 2026 aims to foster collaboration, thought leadership, and community building. By addressing critical challenges such as securing AI/ML systems, ensuring privacy, and understanding the societal impacts of AI, the event supports the advancement of knowledge and solutions in the rapidly evolving field of AI security.